JP6968355B1 - Information processing equipment, information processing methods and programs - Google Patents

Abstract

PROBLEM TO BE SOLVED: To output information capable of specifying a customer's purchasing tendency. SOLUTION: An information processing apparatus 1 includes customer data including a history of changes in a customer rank that fluctuates according to a purchase record of a customer's purchase in a predetermined period in the past, and a customer purchases the product in a predetermined period. A variable customer who is a customer whose customer rank has changed to a predetermined rank for each customer based on the acquisition unit 122 that acquires the purchase history data indicating the history of the purchase and the customer data and the purchase history data. A data generator 123 that generates aggregated data in which information indicating whether or not there is a customer and a category purchase count indicating the number of times a product belonging to a product category has been purchased, and a plurality of product categories based on the aggregated data. Of the combinations, the specific unit 124 that specifies the combination of the product categories that are relatively high in the ratio of purchases by the variable customers, the output unit 126 that outputs the information indicating the combination of the product categories specified by the specific unit 124, and the output unit 126. Have. [Selection diagram] Fig. 2

Description

The present invention relates to an information processing apparatus, an information processing method and a program.

Conventionally, as one of the measures for promoting the purchasing motivation of customers, it has been carried out to give customers benefits such as coupons. Patent Document 1 describes a system for giving a privilege to a customer.

JP-A-2007-109129

However, even if the customer is given a privilege, it may not be possible to promote the customer's purchasing motivation. There are various types of customers, such as customers who frequently use stores and customers who use stores infrequently, and the purchasing tendency of customers differs depending on the type. In order to promote customers' purchasing motivation, it is effective to give benefits according to the purchasing tendency of the customer who is the target of the measure, so it is necessary to identify the purchasing tendency of the customer who is the target of the measure. Has been done.

The present invention has been made in view of the above points, and an object of the present invention is to output information that can identify a customer's purchasing tendency.

The information processing apparatus according to the first aspect of the present invention includes customer data including a history of changes in a customer rank that fluctuates according to a purchase record of a customer purchasing a product in a predetermined period in the past, and said in the predetermined period. Based on the acquisition unit that acquires the purchase history data indicating the purchase history of the customer and the customer data and the purchase history data, the customer rank is a predetermined rank for each customer in the predetermined period. A data generation unit that generates aggregated data in which information indicating whether or not the customer is a variable customer and the number of purchases of the category indicating the number of times a product belonging to the product category has been purchased, and the above-mentioned aggregation Based on the data, the specific unit that specifies the combination of the product categories with a relatively high ratio of purchases by the variable customer among the combinations of the plurality of product categories, and the product category specified by the specific unit. It has an output unit that outputs information indicating a combination.

The output unit may further output information indicating the customer who purchased a plurality of products corresponding to the combination of the product categories specified by the specific unit in the predetermined period among the variable customers.

In the specific unit, among the combinations of the plurality of product categories, the proportion of the variable customers whose number of purchases in the category of each product category satisfies the reference number of times determined for each product category is relatively high. The combination may be specified.

The information processing apparatus may further have a designated designated store or a reception unit that accepts a designated designated range, and the acquisition unit may be the designated store or a plurality of stores existing in the designated range. The purchase history data indicating the history of the purchase of the product by the customer may be acquired.

The acquisition unit acquires the customer data corresponding to the customer having a designated attribute indicating the attribute of the designated customer and the purchase history data indicating the history of the customer having purchased the product having the designated attribute. You may.

The specific unit may specify a combination of the product categories corresponding to the excellent customer, which is the variable customer, whose customer rank has risen from less than the excellent reference rank, which is the predetermined rank, to the superior reference rank or higher. ..

The specific unit may specify a combination of the product categories corresponding to customers other than the variable customer whose customer rank has dropped from the separation reference rank or higher, which is the predetermined rank, to less than the separation reference rank.

The information processing apparatus may further have a learning unit that causes a machine learning model to learn the purchasing tendency of the customer by using the aggregated data, and the specific unit may use the learned machine learning model to learn the learning unit. The combination of product categories may be specified by outputting information indicating the combination of product categories.

The information processing method according to the second aspect of the present invention includes customer data executed by a computer, including a history of changes in the customer rank that changes according to the purchase record of the purchase of the product, and the above-mentioned. Based on the step of acquiring the purchase history data indicating the history of the purchase of the product by the customer in the predetermined period and the customer data and the purchase history data, the customer rank for each customer in the predetermined period. A step to generate aggregated data in which information indicating whether or not a customer is a variable customer who has changed to a predetermined rank and a category purchase number indicating the number of times a product belonging to a product category has been purchased is associated with the step. Based on the aggregated data, a step of specifying a combination of the product categories having a relatively high ratio of purchases by the variable customers among a plurality of combinations of the product categories and a combination of the specified product categories are shown. It has a step to output information.

The program according to the third aspect of the present invention is a computer in which customer data including a history of changes in a customer rank over a predetermined period of time, which changes according to the purchase record of the customer's purchase of a product, and the predetermined period. Based on the acquisition unit that acquires the purchase history data indicating the purchase history of the customer, the customer data and the purchase history data, the customer rank is a predetermined rank for each customer in the predetermined period. A data generation unit that generates aggregated data in which information indicating whether or not the customer is a variable customer and the number of purchases of the category indicating the number of times a product belonging to the product category has been purchased is associated with the aggregated data. A specific unit that specifies a combination of the product categories with a relatively high ratio of purchases by the variable customer among a plurality of combinations of the product categories, and a combination of the product categories specified by the specific unit. A program to function as an output unit that outputs information indicating.

The information processing apparatus according to the fourth aspect of the present invention includes customer data including a history of changes in a customer rank that fluctuates according to a purchase record in which a customer has purchased a product in a predetermined period in the past, and said in the predetermined period. Based on the acquisition unit that acquires the purchase history data indicating the history of the customer's purchase of the product at the store, and the customer data and the purchase history data, the customer rank is determined for each customer in the predetermined period. A data generation unit that generates aggregated data in which information indicating whether or not a customer is a variable customer who has changed to the rank of the customer and the number of times the customer has visited the store in the predetermined period is associated with the data generation unit. Based on the aggregated data, the specific unit that specifies the standard number of store visits for which the ratio of the variable customers is relatively high among the number of store visits of each customer and the information indicating the standard number of store visits specified by the specific unit are output. It has an output unit and an output unit.

According to the present invention, it is possible to output information that can identify the purchasing tendency of the customer.

It is a schematic diagram of an information processing system. It is a block diagram of an information processing apparatus. It is a figure which shows an example of the structure of the database stored in the storage part. It is a figure which represented an example of aggregated data schematically. It is a figure which represented the combination of a plurality of product categories schematically. It is a sequence diagram which shows the processing flow of an information processing apparatus.

[Overview of information processing system S]
FIG. 1 is a schematic diagram of the information processing system S. The information processing system S is a system used to provide information that can identify a customer's purchasing tendency to a manager who manages a store that sells products. Goods include goods and services purchased by customers. The information processing system S includes an information processing device 1 and an information terminal 2. The information processing system S may have other devices such as a server and a terminal.

The information processing device 1 is a computer that outputs information that can identify a customer's purchasing tendency. The information processing device 1 can communicate with the information terminal 2 via a network such as the Internet or a local area network. The information processing device 1 stores in advance customer data indicating information about the customer and purchase history data indicating the history of the customer purchasing the product in the storage unit 11.

The customer data includes information that can identify the customer (customer ID (identifier)), a history of changes in the customer rank of the customer, and the like. The customer rank is a rank that fluctuates according to the purchase record of the customer purchasing the product, and is determined based on, for example, the total amount of the purchase price of the product in one month and the customer rank of the previous month.

The purchase history data includes, for example, the customer ID of the customer who purchased the product, the purchase date, the product category to which the purchased product belongs, and the like. The purchase date may be the date on which the customer purchased the product, or the date and time on which the customer purchased the product. The information processing device 1 acquires customer data and purchase history data from one or a plurality of providers and stores them in the storage unit 11.

The information terminal 2 is a computer that displays information output by the information processing device 1. The information terminal 2 is, for example, a mobile terminal such as a smartphone or a tablet terminal, or a personal computer. The information terminal 2 has a display unit such as a liquid crystal display for displaying information.

The outline of the process in which the information processing system S outputs information that can identify the purchasing tendency of the customer will be described below. When the manager who manages the information processing system S receives a request from the store manager to provide the above information and inputs the measure information based on the content of the measure presented by the manager on the information terminal 2, information processing is performed. The device 1 receives the measure information via the information terminal 2. The measure information includes at least the future measure period, but is not limited to this, and various information may be included. The measure information may include, for example, a designated store designated by the administrator, a designated range designated by the administrator, a designated attribute indicating the attribute of the customer designated by the administrator, and the like.

Of the customer data and purchase history data stored in the storage unit 11, the information processing apparatus 1 acquires customer data corresponding to a predetermined period in the past and purchase history data corresponding to the predetermined period. The predetermined period is a period determined according to the measure period included in the measure information, and is, for example, a period at the same time as the measure period in the most recent past year. For example, if the measure period is the future 3 months from June 2021 to August 2021, the predetermined period is the past 3 months from June 2020 to August 2021.

The information processing device 1 generates aggregated data based on the acquired customer data and purchase history data. The aggregated data is information indicating whether or not the customer is a variable customer whose customer rank has changed to a predetermined rank in a predetermined period for each customer, and category purchase indicating the number of times a product belonging to the product category has been purchased. The data associated with the number of times. The variable customer is either an excellent customer or a non-separate customer, which will be described later, and the target is determined according to the purpose of the measure, for example. The predetermined rank is a standard rank for determining whether or not the customer is a variable customer, a rank for determining whether or not the customer is a superior customer, and whether or not the customer is a non-separable customer. Includes two types of ranks, one for determining whether or not.

Based on the generated aggregated data, the information processing apparatus 1 identifies a combination of product categories in which the ratio of purchases by variable customers is relatively high among the combinations of a plurality of product categories. Then, the information processing apparatus 1 outputs union information indicating the combination of the specified product categories.

By doing so, the information processing system S can output information that can specify the purchasing tendency of a specific customer. For example, if the purpose of the measure is to increase the number of customers who are good customers, the store owner should give the customers the benefits available for each product included in the combination of product categories provided. Thereby, it is possible to provide the motivation for the customer to which the privilege is given to behave in the same manner as the superior customer. Also, for example, if the purpose of the measure is to reduce the number of customers who are alienated customers, the store owner can use it for products in product categories other than the product categories included in the combination of product categories provided. By granting the award to the customer, it is possible to provide the customer to which the award is granted the same purchasing behavior as the non-removal customer, that is, the motivation to behave differently from the estranged customer. Customers with many product categories of purchased products tend to have higher customer ranks than customers with few product categories of purchased products. Therefore, by implementing such measures, more customers will be given. You can encourage the purchase of products in the product category. As a result, the information processing system S can improve the sales of the store.
Hereinafter, the configuration of the information processing apparatus 1 will be described.

[Configuration of information processing device 1]
FIG. 2 is a block diagram of the information processing apparatus 1. In FIG. 2, the arrows indicate the main data flows, and there may be data flows other than those shown in FIG. In FIG. 2, each block shows not a hardware (device) unit configuration but a functional unit configuration. Therefore, the block shown in FIG. 2 may be mounted in a single device, or may be mounted in a plurality of devices separately. Data can be exchanged between blocks via any means such as a data bus, a network, and a portable storage medium.

The information processing device 1 has a storage unit 11 and a control unit 12. The storage unit 11 is a storage medium including a ROM (Read Only Memory), a RAM (Random Access Memory), a hard disk drive, and the like. The storage unit 11 stores in advance the program executed by the control unit 12. The storage unit 11 may be provided outside the information processing device 1, and in that case, data may be exchanged with the control unit 12 via a network. The storage unit 11 stores a customer management database that manages customer data and a purchase history database that manages purchase history data.

FIG. 3 is a diagram showing an example of the configuration of the database stored in the storage unit 11. The customer management database shown in FIG. 3A associates a customer ID as an example of information that can identify a customer, a customer's gender, a customer's age, a customer's address, a fluctuation history, and a customer's characteristics. I remember. The fluctuation history is information indicating the history of past fluctuations in the customer rank, and is, for example, information indicating the monthly customer rank.

The customer characteristic is information indicating the purchasing tendency of the customer, and is represented by a numerical value (index) for each type of customer characteristic, for example. The types of customer characteristics are, for example, early adopters that indicate customers who tend to purchase launched products early, price-sensitive products that indicate customers who tend to purchase products at a lower price than the regular price, and purchase limited products. Includes limited merchandise purchases that indicate customers who tend to purchase health-related merchandise, health-related merchandise purchases that indicate customers that tend to purchase health-related merchandise, and premium merchandise purchases that indicate customers who tend to purchase premium merchandise. The information processing apparatus 1 calculates an index of each customer characteristic for each customer based on the purchase history data and stores it in the customer management database. The customer management database is not limited to the example shown in FIG. 3A, and may further store various information such as a customer's name and address.

The purchase history database shown in FIG. 3 (b) includes the customer ID of the customer who purchased the product, the purchase date when the customer purchased the product, the product category to which the purchased product belongs, and the store where the product was purchased. The store name and the address of the store are stored in association with each other. The product category is information indicating the type of product. The purchase history data is not limited to the example shown in FIG. 3 (b), but includes the name of the product purchased by the customer, the price of the product, the total price of the product purchased by the customer in one day or one purchase, and the like. Various information may be further stored.

Returning to FIG. 2, the control unit 12 is, for example, a processor such as a CPU (Central Processing Unit), and by executing a program stored in the storage unit 11, the reception unit 121, the acquisition unit 122, and the data generation unit 123, It functions as a specific unit 124, a learning unit 125, and an output unit 126. At least some of the functions of the control unit 12 may be performed by an electric circuit. Further, at least a part of the functions of the control unit 12 may be executed by a program executed via the network.

The reception unit 121 accepts input of measure information based on the content of the measure. The reception unit 121 acquires, for example, the measure information input by the information terminal 2. For example, the information processing device 1 has an operation unit (for example, a keyboard, a mouse, a touch panel superimposed on a display, etc.) (not shown), and the reception unit 121 inputs measure information via the operation unit. You may accept it.

The acquisition unit 122 acquires information used by the specific unit 124, which will be described later, to specify a combination of product categories. Specifically, the acquisition unit 122 includes customer data including a history of changes in the customer rank in the past predetermined period, which fluctuates according to the purchase record of the customer purchasing the product, and the customer purchases the product in the predetermined period. Acquires the purchase history data indicating the history of the purchase. More specifically, when the reception unit 121 receives the measure information including the measure period, the acquisition unit 122 refers to the customer management database and customer data including the fluctuation history of a predetermined period determined according to the measure period. Is extracted, and the purchase history data whose purchase date is included in the predetermined period is extracted by referring to the purchase history data.

The acquisition unit 122 may acquire purchase history data indicating a history in which a customer has purchased a product at a predetermined store. Specifically, when the reception unit 121 accepts the input of the measure information including the designated store designated by the administrator or the designated range specified by the administrator, the acquisition unit 122 may have a plurality of units existing in the designated store or the designated range. Acquire purchase history data showing the history of customers purchasing products at the store.

For example, when the reception unit 121 accepts the input of the measure information including the designated store, the acquisition unit 122 refers to the purchase history database and extracts the purchase history data whose store name corresponds to the designated store. Further, for example, when the reception unit 121 accepts the input of the measure information including the designated store, the acquisition unit 122 refers to the purchase history database and inputs the purchase history data corresponding to the store whose store address is included in the designated range. Extract. By doing so, the information processing apparatus 1 can specify a combination of product categories specialized for a specific store or a specific area.

The acquisition unit 122 may acquire customer data corresponding to a customer having a predetermined attribute and purchase history data indicating a history in which the customer having the predetermined attribute has purchased a product. A given attribute is at least one of a customer's gender, age (age), and customer characteristics.

Specifically, when the reception unit 121 receives the measure information including the designated attribute indicating the attribute of the customer designated by the administrator, the acquisition unit 122 receives the customer data corresponding to the customer having the designated attribute and the designated attribute. The purchase history data indicating the history of the purchase of the product by the customer having the above is acquired. For example, when the reception unit 121 receives the measure information including the gender (for example, female) or the age (for example, 30s) as the designated attribute, the acquisition unit 122 refers to the customer management database and has the same gender or the same gender as the designated attribute. The customer data corresponding to the customer of the age included in the age of the specified attribute is extracted, and the purchase history data corresponding to the customer of the customer data extracted by referring to the purchase history data is extracted.

Further, for example, when the reception unit 121 receives the measure information including a specific customer characteristic (for example, an early adapter) as a designated attribute, the acquisition unit 122 refers to the customer management database and has a large index of the customer characteristic early adapter. Customer data corresponding to a customer (for example, a customer whose index is equal to or higher than a predetermined threshold) is extracted, and purchase history data corresponding to the customer in the customer data extracted by referring to the purchase history data is extracted. By doing so, the information processing apparatus 1 can specify a combination of product categories specialized for a customer having a predetermined attribute.

The acquisition unit 122 may acquire customer data and purchase history data based on customer characteristics according to the product to be promoted. For example, when the reception unit 121 receives the measure information including the information indicating that the product to be promoted is a newly released product, the acquisition unit 122 receives the customer data corresponding to the customer having a large early adopter index and the corresponding customer data. Get the purchase history data corresponding to the customer.

Based on the customer data and the purchase history data, the data generation unit 123 includes variable information indicating whether or not the customer is a variable customer whose customer rank has changed to a predetermined rank in a predetermined period for each customer. Generate aggregated data associated with the number of category purchases that indicate the number of times a product belonging to a product category has been purchased. The data generation unit 123 is not limited to this, and may generate aggregated data to which various information is further associated.

FIG. 4 is a diagram schematically showing an example of aggregated data. As shown in FIG. 4, in the aggregated data, the customer ID, the fluctuation information, and the number of category purchases of each product category are associated with each other. The data generation unit 123 generates aggregated data as shown in FIG. 4 based on the customer data and the purchase history data. "Variable" in the variable information indicates a variable customer who is a customer whose customer rank has changed to a predetermined rank in a predetermined period, and "no change" in the variable information indicates that the customer rank has changed to a predetermined rank in a predetermined period. Indicates a non-variable customer who is a non-variable customer.

Returning to FIG. 2, the specifying unit 124 identifies a combination of product categories in which the ratio of purchases by variable customers is relatively high among the combinations of a plurality of product categories based on the aggregated data. Specifically, the specific unit 124 changes the customer rank of the variable customer in a predetermined period based on the aggregated data, in the order of the product category having a high degree of influence (hereinafter, simply referred to as “the product category having a high degree of influence”). , The combination of the above product categories is specified by specifying the product categories in which the ratio of purchases by variable customers is relatively high. The "highly influential product category" is a product category in which the number of purchases by a customer whose customer rank has changed in a predetermined period is larger than the number of purchases by a customer whose customer rank has not changed in a predetermined period. ..

More specifically, the specific unit 124 shows the ratio of variable customers to all customers (all customers included in the customer data acquired by the acquisition unit 122) for each combination of product categories based on the aggregated data. Calculate the volatility and identify the combination of product categories with relatively high volatility. The specifying unit 124 identifies, for example, the combination of the product categories having the highest volatility among the combinations of the plurality of product categories based on the aggregated data.

The specific unit 124 may specify a combination of product categories having a relatively high ratio of variable customers based on a combination of a plurality of product categories and a reference number of times determined for each product category. Specifically, in the specific unit 124, the ratio of variable customers whose category purchase count of each product category meets the standard number of times set for each product category among the combinations of a plurality of product categories is based on the aggregated data. Identify relatively high product category combinations.

More specifically, first, the specific unit 124 specifies the number of purchases at the boundary where the difference between the number of variable customers and the number of non-variable customers is large for each product category as the reference number based on the aggregated data. do. The specifying unit 124 specifies, for example, the number of purchases in which the difference between the number of variable customers and the number of non-variable customers exceeds a predetermined threshold value as a reference number of times. Then, the specifying unit 124 specifies a combination of product categories in which the proportion of variable customers whose category purchase count of each product category satisfies the specified reference number of times is relatively high among the combinations of the plurality of product categories.

FIG. 5 is a diagram schematically showing a combination of a plurality of product categories. In FIG. 5, the product categories are represented by a tree hierarchy (first hierarchy T1, second hierarchy T2, third hierarchy T3), and the higher the hierarchy (for example, the first hierarchy T1), the higher the degree of influence of the product categories. Shown, the lower the hierarchy (for example, the third hierarchy T3), the lower the degree of influence indicates the product category. In FIG. 5, eight patterns from patterns P1 to P8 are shown as patterns that combine the combination of product categories and whether or not the number of purchases of each product category is equal to or greater than the reference number of times.

The volatility of 15% shown in the upper part of FIG. 5 is a volatility showing the ratio of variable customers to all customers. For example, the number of purchases of the product category “DIY” in the first layer T1 is 17 times, which is the reference number. If the above is true (YES), the volatility is 38%, and if the number of purchases is less than 17 (NO), the volatility is 6%. In the example shown in FIG. 5, the specifying unit 124 calculates the volatility of each pattern and specifies the combination of product categories indicated by the pattern with the highest volatility among the calculated volatility of each pattern. By doing so, the information processing apparatus 1 can narrow down the combinations of product categories having a high volatility.

Returning to FIG. 2, the specifying unit 124 may specify a combination of product categories corresponding to a specific variable customer. Floating customers include good customers and non-leaving customers. A good customer is a variable customer whose customer rank has risen from less than the good standard rank, which is a predetermined rank, to higher than the good standard rank. The excellent reference rank is, for example, A rank when the customer rank is classified into six stages of S rank, A rank, B rank, C rank, D rank, and E rank in descending order of rank. A non-removal customer is a customer other than a estranged customer whose customer rank has dropped from a predetermined rank of the estrangement reference rank or higher to less than the estrangement reference rank. The separation reference rank is, for example, the D rank when the customer rank is classified in the above six stages.

Specifically, when the reception unit 121 receives the measure information including the designated variable customer designated by the administrator, and the designated variable customer indicates the excellent customer, the specific unit 124 corresponds to the excellent customer. Identify the combination of product categories you want to do. On the other hand, when the reception unit 121 receives the measure information including the designated variable customer and the designated variable customer indicates a non-removal customer, the specific unit 124 specifies a combination of product categories corresponding to the non-removal customer. By doing so, the information processing apparatus 1 can specify a combination of product categories specialized for a specific variable customer.

The specific unit 124 may specify the combination of product categories by using a machine learning model trained to output the combination of product categories by inputting the measure information. The machine learning model is a model generated by using a known machine learning algorithm such as a random forest.

Specifically, first, the learning unit 125 causes the machine learning model to learn the purchasing tendency of the customer by using the aggregated data. Then, the specifying unit 124 specifies the combination of product categories by outputting the union information indicating the combination of product categories to the machine learning model in which the purchasing tendency of the customer is learned. For example, when the reception unit 121 accepts the input of the measure information, the specific unit 124 outputs the combination of product categories to the machine learning model by inputting the measure information into the machine learning model in which the customer's purchasing tendency is learned. Let me. By doing so, the information processing apparatus 1 can identify a combination of product categories in which the ratio of purchases by variable customers is relatively high, using a large amount of data.

The output unit 126 outputs union information indicating a combination of product categories specified by the specific unit 124. Specifically, the output unit 126 transmits the union information indicating the combination of the product categories specified by the specific unit 124 to the information terminal 2. The output unit 126 is not limited to this, and may output the union information by printing on paper using a printer, storing in a storage medium, or transmitting to the outside by communication. Store owners who are provided with such information can implement measures to encourage customers' purchasing motivation based on a combination of product categories with a relatively high percentage of purchases by variable customers. ..

The output unit 126 may further output information indicating a customer corresponding to the combination of product categories specified by the specific unit 124. Specifically, the output unit 126 further outputs information indicating a customer who has purchased a plurality of products corresponding to the combination of the product categories specified by the specific unit 124 among the variable customers in a predetermined period. The output unit 126 may output information indicating a customer whose customer rank does not satisfy a predetermined condition among the customers who have purchased a plurality of products corresponding to the combination of the product categories specified by the specific unit 124.

For example, when the purpose of the measure is to increase the number of customers who are excellent customers, the output unit 126 is currently among the customers who have purchased a plurality of products corresponding to the combination of the product categories specified by the specific unit 124. Outputs information indicating a customer whose customer rank is less than the excellent reference rank (for example, A rank). Further, for example, when the purpose of the measure is to reduce the number of customers who are alienated customers, the output unit 126 is among the customers who have purchased a plurality of products corresponding to the combination of the product categories specified by the specific unit 124. Outputs information indicating a customer whose current customer rank is the separation reference rank (for example, D rank).

For example, the output unit 126 outputs variable customers who have purchased a plurality of products corresponding to the combination of the product categories specified by the specific unit 124 in descending order of the total number of times the category purchases of each product category are totaled. The output unit 126 may output information indicating customers for a predetermined number of people (for example, 100 people) in descending order of the total number of times. By doing so, the store owner can take measures for a specific customer.

[Processing of information processing device 1]
Subsequently, the processing flow of the information processing apparatus 1 will be described. FIG. 6 is a sequence diagram showing a processing flow of the information processing apparatus 1. This process starts when the reception unit 121 accepts the input of the measure information including the period information (S1).

The acquisition unit 122 acquires customer data corresponding to a predetermined period determined by the period information included in the measure information and purchase history data corresponding to the predetermined period (S2). Based on the customer data and the purchase history data, the data generation unit 123 includes variable information indicating whether or not the customer is a variable customer whose customer rank has changed to a predetermined rank in a predetermined period for each customer. Generates aggregated data associated with the number of category purchases indicating the number of times a product belonging to a product category has been purchased (S3).

Based on the aggregated data, the specifying unit 124 identifies a combination of product categories in which the ratio of purchases by variable customers is relatively high among the combinations of a plurality of product categories (S4). Then, the output unit 126 outputs the union information indicating the combination of the product categories specified by the specific unit 124 (S5).

[Modification example]
In the above, the information processing apparatus 1 has described an example of outputting union information indicating a combination of product categories, but the present invention is not limited to this. For example, the information processing apparatus 1 may output information indicating the number of visits to the store, which is a reference for variable customers. The number of visits is, for example, the number of times a customer has purchased a product based on purchase history data.

In this case, first, the data generation unit 123 determines whether or not the customer is a variable customer whose customer rank has changed to a predetermined rank in a predetermined period for each customer based on the customer data and the purchase history data. Generates aggregated data in which the information shown is associated with the number of visits the customer has made to the store over a given period of time. Based on the aggregated data, the specifying unit 124 specifies the standard number of store visits in which the ratio of variable customers is relatively high among the number of store visits of each customer. The specifying unit 124 specifies, for example, the number of store visits at the boundary where the difference between the number of variable customers and the number of non-variable customers is large (for example, the number of store visits exceeding a predetermined threshold value) as the standard number of store visits. ..

Then, the output unit 126 outputs information indicating the standard number of visits specified by the specific unit 124. By doing so, the manager of the store to which the above information is provided can take measures according to the specified standard number of visits to the store. For example, a store owner can determine how often a benefit should be granted to a customer based on the specified criteria number of visits.

Further, the information processing device 1 may output information indicating not only the standard number of visits to the store but also the standard amount of money for the variable customer (total amount of products purchased by the customer in a predetermined period). In this case, first, the data generation unit 123 determines, for each customer, the statistical value of the total amount of the products purchased by the customer in each second period included in the first period, based on the customer data and the purchase history data. Aggregate data associated with information indicating whether or not the customer is a variable customer who is a customer whose customer rank has changed to a predetermined rank in the first period is generated. The first period is a predetermined period (for example, 3 months, 6 months, 12 months, etc.), and the second period is a shorter period than the first period (for example, 1 week, 1 month, etc.). Is. The statistic is, for example, the average, median, or mode of the total amount of each second period.

The specifying unit 124 identifies a reference statistical value in which the ratio of variable customers is relatively high among the statistical values of each customer based on the aggregated data. Then, the output unit 126 outputs information indicating the specific result specified by the specific unit 124. In this way, the store owner can determine how many products, or at what price, should be given to the customer based on the identified baseline statistics. Can be done.

Further, in the information processing device 1, among the combinations of the plurality of product categories, the number of visits to the store in the predetermined period is equal to or greater than the standard number of visits to the store, and the total amount of the products purchased in the predetermined period is equal to or greater than the above statistical value. A combination of product categories with a relatively high percentage of purchases by variable customers satisfying at least one of the above may be specified and union information indicating the combination of the specified product categories may be output. By doing so, the information processing apparatus 1 can output information that can specify the purchasing tendency of a specific customer with higher accuracy.

[Effects in this embodiment]
As described above, the information processing apparatus 1 is based on customer data including a history of changes in the customer rank in the past predetermined period and purchase history data indicating a history in which the customer purchased a product in the predetermined period. For each customer, the fluctuation information indicating whether or not the customer is a variable customer whose customer rank has changed to a predetermined rank in a predetermined period, and the number of category purchases indicating the number of times a product belonging to the product category has been purchased are obtained. Generate the associated aggregated data. Then, the information processing apparatus 1 identifies the combination of the product categories in which the ratio of purchases by the variable customers is relatively high among the combinations of the plurality of product categories based on the aggregated data, and selects the combination of the specified product categories. Output the indicated union information.

By doing so, the information processing apparatus 1 can output information that can identify the purchasing tendency of a specific customer. For example, if the purpose of the measure is to increase the number of customers who are good customers, the store owner should give the customers the benefits available for each product included in the combination of product categories provided. Thereby, it is possible to provide the motivation for the customer to which the privilege is given to behave in the same manner as the superior customer. Also, for example, if the purpose of the measure is to reduce the number of customers who are alienated customers, the store owner can use it for products in product categories other than the product categories included in the combination of product categories provided. By granting the award to the customer, it is possible to provide the customer to which the award is granted the same purchasing behavior as the non-removal customer, that is, the motivation to behave differently from the estranged customer. As a result, the information processing apparatus 1 can improve the sales of the store.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes can be made within the scope of the gist. be. For example, all or part of the device can be functionally or physically distributed / integrated in any unit. Also included in the embodiments of the present invention are new embodiments resulting from any combination of the plurality of embodiments. The effect of the new embodiment produced by the combination has the effect of the original embodiment together.

1 Information processing device 11 Storage unit 12 Control unit 121 Reception unit 122 Acquisition unit 123 Data generation unit 124 Specific unit 125 Learning unit 126 Output unit 2 Information terminal S Information processing system

Claims (9)

Customer data including a history of changes in the customer rank in the past predetermined period, which fluctuates according to the purchase record of the customer purchasing the product, and purchase history data showing the history of the customer purchasing the product in the predetermined period. And the acquisition department to acquire
Based on the customer data and the purchase history data, information indicating whether or not the customer is a variable customer whose customer rank has changed to a predetermined rank in the predetermined period and a product category for each customer. A data generator that generates aggregated data associated with the number of purchases in a category that indicates the number of times products belonging to the category have been purchased.
Based on the aggregated data, for each of the product categories, the number of the variable customers who purchased the products belonging to the product category more than the predetermined number of purchases in the category among the plurality of variable customers and the customers other than the variable customers. The reference number of times that the difference from the number of the unchanging customers who purchased the product belonging to the product category more than the number of purchases in the predetermined category among a plurality of unchanging customers exceeds the predetermined threshold is the number of purchases in the predetermined category. A plurality of the above-mentioned patterns in which a plurality of the specified product categories are combined, including whether or not the number of times the customer purchases a product belonging to the product category is equal to or greater than the reference number of times corresponding to the product category. For each pattern, a fluctuation rate indicating the ratio of the variable customer to a plurality of customers corresponding to the pattern is calculated, and among the plurality of patterns, the product category indicated by the pattern having a relatively high fluctuation rate. With a specific part that identifies the combination of
An output unit that outputs information indicating a combination of the product categories specified by the specific unit, and an output unit.
Information processing device with.
The output unit further outputs information indicating the customer who has purchased a plurality of products corresponding to the combination of the product categories specified by the specific unit in the predetermined period among the variable customers.
The information processing apparatus according to claim 1. It also has a reception desk that accepts designated designated stores or designated ranges.
The acquisition unit acquires the purchase history data indicating the history of the customer purchasing the product at the designated store or a plurality of stores existing in the designated range.
The information processing apparatus according to claim 1 or 2. The acquisition unit acquires the customer data corresponding to the customer having a designated attribute indicating the designated attribute of the customer and the purchase history data indicating the history of the customer having purchased the product having the designated attribute. do,
The information processing apparatus according to any one of claims 1 to 3. The specific unit identifies a combination of the product categories corresponding to the excellent customer, which is the variable customer, whose customer rank has risen from less than the excellent reference rank, which is the predetermined rank, to the superior reference rank or higher.
The information processing apparatus according to any one of claims 1 to 4. The specific unit specifies a combination of the product categories corresponding to customers other than the variable customer whose customer rank has dropped from the separation reference rank or higher, which is the predetermined rank, to less than the separation reference rank.
The information processing apparatus according to any one of claims 1 to 4. Computer runs,
Customer data including a history of changes in the customer rank in the past predetermined period, which fluctuates according to the purchase record of the customer purchasing the product, and purchase history data showing the history of the customer purchasing the product in the predetermined period. And the steps to get
Based on the customer data and the purchase history data, information indicating whether or not the customer is a variable customer whose customer rank has changed to a predetermined rank in the predetermined period and a product category for each customer. A step that generates aggregated data associated with the number of purchases in a category that indicates the number of times a product belonging to belongs to.
Based on the aggregated data, for each of the product categories, the number of the variable customers who purchased the products belonging to the product category more than the predetermined number of purchases in the category among the plurality of variable customers and the customers other than the variable customers. The reference number of times that the difference from the number of the unchanging customers who purchased the product belonging to the product category more than the number of purchases in the predetermined category among a plurality of unchanging customers exceeds the predetermined threshold is the number of purchases in the predetermined category. Steps to identify and
A pattern in which a plurality of the product categories are combined, and for each of the plurality of the patterns including whether or not the number of times the customer purchases a product belonging to the product category is equal to or greater than the reference number of times corresponding to the product category. On the other hand, a step of calculating a fluctuation rate indicating the ratio of the variable customer to a plurality of customers corresponding to the pattern, and
A step of specifying a combination of the product categories indicated by the pattern having a relatively high volatility among the plurality of patterns, and a step of specifying the combination.
A step to output information indicating the combination of the specified product categories, and
Information processing method with. Computer,
Customer data including a history of changes in the customer rank in the past predetermined period, which fluctuates according to the purchase record of the customer purchasing the product, and purchase history data showing the history of the customer purchasing the product in the predetermined period. To get the acquisition department,
Based on the customer data and the purchase history data, information indicating whether or not the customer is a variable customer whose customer rank has changed to a predetermined rank in the predetermined period and a product category for each customer. A data generator that generates aggregated data associated with the number of purchases in a category that indicates the number of times a product belongs to
Based on the aggregated data, for each of the product categories, the number of the variable customers who purchased the products belonging to the product category more than the predetermined number of purchases in the category among the plurality of variable customers and the customers other than the variable customers. The reference number of times that the difference from the number of the unchanging customers who purchased the product belonging to the product category more than the number of purchases in the predetermined category among a plurality of unchanging customers exceeds the predetermined threshold is the number of purchases in the predetermined category. A plurality of the above-mentioned patterns in which a plurality of the specified product categories are combined, including whether or not the number of times the customer purchases a product belonging to the product category is equal to or greater than the reference number of times corresponding to the product category. For each pattern, a fluctuation rate indicating the ratio of the variable customer to a plurality of customers corresponding to the pattern is calculated, and among the plurality of patterns, the product category indicated by the pattern having a relatively high fluctuation rate. A specific unit that specifies a combination of products, and an output unit that outputs information indicating a combination of the product categories specified by the specific unit.
A program to function as. Customer data including a history of changes in the customer rank over a predetermined period of time, which fluctuates according to the purchase record of the customer purchasing the product, and a purchase history showing the history of the customer purchasing the product at the store during the predetermined period. The acquisition unit that acquires data and
Based on the customer data and the purchase history data, information indicating whether or not the customer is a variable customer whose customer rank has changed to a predetermined rank in the predetermined period and the predetermined value for each customer. a data generating unit that the customer is to produce the aggregated data associated with and the number of purchases you made a purchase in a store in the period,
Of the number of purchases by each customer, based on the magnitude of the difference between the number of purchases of the variable customer indicated by the aggregated data and the number of purchases of the customer other than the variable customer indicated by the aggregated data. , The specific part that specifies the standard number of purchases with a relatively high percentage of variable customers,
An output unit that outputs information indicating the reference purchase number of times specified by the specific unit, and an output unit.
Information processing device with.

Images